“The best simple argument for Pausing AI?” by Gary Marcus
No se pudo agregar al carrito
Solo puedes tener X títulos en el carrito para realizar el pago.
Add to Cart failed.
Por favor prueba de nuevo más tarde
Error al Agregar a Lista de Deseos.
Por favor prueba de nuevo más tarde
Error al eliminar de la lista de deseos.
Por favor prueba de nuevo más tarde
Error al añadir a tu biblioteca
Por favor intenta de nuevo
Error al seguir el podcast
Intenta nuevamente
Error al dejar de seguir el podcast
Intenta nuevamente
“The best simple argument for Pausing AI?” by Gary Marcus
-
Narrado por:
-
De:
Acerca de esta escucha
- Alignment without the capacity to follow rules is hopeless. You can’t possibly follow laws like Asimov's Laws (or better alternatives to them) if you can’t reliably learn to abide by simple constraints like the rules of chess.
- LLMs can’t reliably follow rules. As discussed in Marcus on AI yesterday, per data from Mathieu Acher, even reasoning models like o3 in fact empirically struggle with the rules of chess. And they do this even though they can explicit explain those rules (see same article). The Apple “thinking” paper, which I have discussed extensively in 3 recent articles in my Substack, gives another example, where an LLM can’t play Tower of Hanoi with 9 pegs. (This is not a token-related artifact). Four other papers have shown related failures in compliance with moderately complex rules in the last month.
- [...]
First published:
June 30th, 2025
Source:
https://www.lesswrong.com/posts/Q2PdrjowtXkYQ5whW/the-best-simple-argument-for-pausing-ai
---
Narrated by TYPE III AUDIO.
Todavía no hay opiniones